oh-my-lilys
Fail
Audited by Snyk on Mar 4, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt instructs use of "lilys auth " (manual token passed on the command line) and auto-extraction of browser tokens, both of which require the agent to handle or include secret values verbatim and thus present a high exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly documents a "summarize " command (examples like "lilys summarize https://youtube.com/watch?v=abc123") that fetches and ingests content from open public sources (YouTube, websites, PDFs, audio), meaning untrusted third‑party content is read and used to generate reports that can influence agent actions.
Audit Metadata